mt5-small-query_realestate_cars-finetuned

This model is a fine-tuned version of google/mt5-small on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.2111
• Rouge1: 51.6261
• Rouge2: 40.1355
• Rougel: 51.6277
• Rougelsum: 51.6154
• Gen Len: 8.9971
• Valid Json: 0.0085

Model description

More information needed

Intended uses & limitations

More information needed

Training and evaluation data

More information needed

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

• learning_rate: 0.0002
• train_batch_size: 4
• eval_batch_size: 4
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 5

Training results

Training Loss	Epoch	Step	Validation Loss	Rouge1	Rouge2	Rougel	Rougelsum	Gen Len	Valid Json
0.4256	1.0	12204	0.2693	50.0289	38.3453	50.0269	50.027	8.9965	0.0061
0.3171	2.0	24408	0.2338	50.1782	38.5868	50.1546	50.1534	8.9985	0.0053
0.2364	3.0	36612	0.2200	51.1478	39.5229	51.1357	51.1351	8.9978	0.0068
0.1869	4.0	48816	0.2130	51.603	39.91	51.5963	51.5877	8.9974	0.0088
0.2221	5.0	61020	0.2111	51.6261	40.1355	51.6277	51.6154	8.9971	0.0085

Framework versions

• Transformers 4.24.0
• Pytorch 1.13.0+cu117
• Datasets 2.8.0
• Tokenizers 0.12.1